Federated learning with Blockchain on Denial-of-Service attacks detection and classification of edge IIoT networks using Deep Transfer Learning model

Abstract

With the rapid evolution of Internet of Things (IoT) and artificial intelligence (AI), the industry 4.0 era has arisen. As per the IBM prediction, by the constant spread of 5G technology, the IoT intend to be more extensively utilized in industries. Recently, federated learning (FL) turned out to be significant focus among Industrial IoT (IIoT) scholars. Conversely, numerous devices in IIoT presently hold an issue of low computational power, so these devices can't able to function well while challenging the updating and training method tasks in FL. The latest development of machine learning (ML) and deep learning (DL) approaches will help to reinforce these IDSs. The secrecy behaviour of these databases and extensive advent of combative outbreaks makes it challenging for main institutions to transmit their fragile data. Therefore, the current study designs a Federated Learning on Denial-of-Service Attacks Detection and Classification using Deep Transfer Learning (FLDoSADC-DTL) model for BC-supported IIoT environment. The aim of the presented FLDoSADC-DTL approach is to recognize the presence of DoS attacks in the BC-based IIoT environment. To enable secure communication in the IIoT networks, BC technology is used. To accomplish this, the FLDoSADC-DTL technique performs sand cat swarm algorithm (SCSA) based feature subset selection. For the DoS attack detection process, a stacked auto-encoder (SAE) model is utilized in this study. Finally, the black widow optimization algorithm (BWOA) can be implemented for hyperparameter tuning of the SAE technique. A widespread of experiments were performed to emphasize the higher performance of FLDoSADC-DTL method. The complete experimentation outcomes indicated the enhanced performance of FLDoSADC-DTL approach over other recent methods.